Near infrared spectrum analyzing method based on isolated component analysis and genetic neural network

A technology of genetic neural network and independent component analysis, applied in the field of near-infrared spectroscopy, can solve the problems of lack of chemical meaning and cannot be used to identify unknown components of mixed spectra, so as to broaden the application range, have good application prospects, and enrich chemometrics The effect of the method

Inactive Publication Date: 2009-09-02
CHINA JILIANG UNIV
View PDF0 Cites 41 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, none of the above chemometric methods can be used to identify unknown components in the mixed spectrum, lacking practical chemical meaning, and has certain limitations

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Near infrared spectrum analyzing method based on isolated component analysis and genetic neural network
  • Near infrared spectrum analyzing method based on isolated component analysis and genetic neural network
  • Near infrared spectrum analyzing method based on isolated component analysis and genetic neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The present invention applies ICA to the analysis of NIR data, first uses discrete wavelet transform to carry out effective compression to near-infrared spectrum data, then uses independent component analysis (ICA) method to extract the independent component of near-infrared spectrum data matrix and corresponding mixing coefficient matrix, Finally, neural network regression was used to model the mixing coefficient matrix and the measured concentration matrix for quantitative analysis of the samples to be tested. Due to the sensitivity of the BP network to the initial value and other issues, the genetic algorithm is used to optimize the network structure and improve the prediction accuracy of the model. This method can not only decompose the spectral information of the main components from the sample spectrum, but also realize the determination of the sample components. The independent components extracted by this method are closer to the actual spectrum, and can better r...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a near infrared spectrum analyzing method based on the isolated component analysis and genetic neural network, which comprises the following steps for the acquired near infrared spectrum: firstly, effectively compressing spectrum data by using wavelet transform; secondly, extracting an independent component and a corresponding mixed coefficient matrix of a near infrared spectrum data matrix by using an isolated component analysis method; thirdly, building a three-layer BP neutral network, using the mixed coefficient matrix of a training sample as the input and correspondingly measured component concentration matrix as the output, and optimizing a neutral network structure by adopting a genetic algorithm, and obtaining a GA-BP neutral network by the training of the training sample; fourthly, predicting and analyzing the measured component concentration of the predicted set sample by using the GA-BA neutral network. The method enriches the chemical measurement method, widens the application range of the isolated component analysis and has favorable application prospect.

Description

technical field [0001] The invention relates to near-infrared spectrum analysis technology, in particular to a quantitative analysis method combining ICA and artificial neural network in near-infrared spectrum analysis. Background technique [0002] Near Infrared Spectroscopy (NIR) is known as the fastest-growing spectral analysis technology since the 1990s. It is an organic combination of spectral measurement technology and chemometrics, and is known as the giant of analysis. It uses the near-infrared absorption spectrum information of the substance, and uses the chemometric method to analyze and process the experimental data, so as to perform qualitative and quantitative analysis and determination of the sample. It is a fast and non-destructive new detection technology. Chemometric methods are the guarantee for the effective application of NIR in quantitative and qualitative analysis, such as common partial least squares (PLS), principal component regression (PCR), artific...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01N21/35G06N3/02G01N21/359
Inventor 林敏方利民
Owner CHINA JILIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap